Machine Learning Application in MicroFinance
Submitted by Anubhav Dikshit on Saturday, 30 April 2016
Artoo is a loan origination system (LOS), our aim is to improve the financial inclusion in world (starting with India). As a testament to our mission we have help disbursed 1 Lac loans worth 1,000 crores (last two years), we wanted to share our experience of using data and eventually data science in helping our clients take the right call while disbursing loans.
MFI in India is one of the most heavily regulated industry, these industries cater to customer who are deemed ‘high risk customers’ by traditional banks. The other alternative to these ‘high risk customers’ are the unregulated loan sharks. The loans given out by these MFI’s tend to have interest rates of 20% and upward at and thus there is a high reward (both to customer and the MFI itself) to reduce operational cost.
Due to the nature of the customer (undocumented income, with no credit history), traditional process to gauge a customer does not suffice (credit bureau report). In order to inspire enough confidence about a customer Artoo captures 800 odd data points about the customer (all captured in the field).
Its Artoo’s belief that, if we help MFI’s become more efficient, accurate and quicker, then this will lead to MFI(s) will in turn reach more people and increasing the financial inclusion. In order to quicken the loan disbursement process during credit underwriting process Artoo points only the data points that are off for a given occupation and geography (income is 25% higher than the trend, household expense much lower than the trend).
An analytics & machine learning enthusiast with experience of close to 2 years. Worked as a field force division for a US based pharmaceutical company, after working for a span of 14 months I joined Artoo a Bangalore Fintech based startup.